DMCA
Using Corpus-derived Name Lists for Named Entity Recognition (2000)
Cached
Download Links
| Venue: | In Proc. of Applied NLP and the N. American Chapter of the ACL |
| Citations: | 18 - 0 self |
BibTeX
@INPROCEEDINGS{Stevenson00usingcorpus-derived,
author = {Mark Stevenson and Robert Gaizauskas},
title = {Using Corpus-derived Name Lists for Named Entity Recognition},
booktitle = {In Proc. of Applied NLP and the N. American Chapter of the ACL},
year = {2000},
pages = {290--295}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper describes experiments to establish the performance of a named entity recognition system which naively builds categorized lists of names from manually annotated training data and then matches names in test data using these lists. Such an approach performs significantly less well than state-ofthe -art NE systems. However, we then show that by using simple filtering techniques for improving the automatically acquired lists, substantial performance benefits can be achieved, with resulting Fmeasure scores of 87 % -- only 5% less than the state-of-the art. These results provide a baseline against which the contribution of more sophisticated supervised learning techniques for NE recognition should be measured. 1 Introduction Named entity (NE) recognition is the process of identifying and categorising names in text. Systems which have attempted the NE task have, in general, made use of lists of common names to provide clues. Name lists provide an extremely efficient way of recogni...
Keyphrases
named entity recognition corpus-derived name list ne recognition resulting fmeasure score training data test data entity recognition system substantial performance benefit categorized list state-ofthe art ne system sophisticated supervised learning technique ne task state-of-the art common name efficient way introduction named entity acquired list
